Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29450
    Prev
    Next
    INDEX
    Explanations

    elements encouraging audience interaction and engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Web
    -0.07
    Web
    -0.07
    _CS
    -0.06
    -c
    -0.06
     web
    -0.06
    959
    -0.06
     Vy
    -0.05
    alle
    -0.05
    ube
    -0.05
    URN
    -0.05
    POSITIVE LOGITS
    subscribe
    0.10
    hani
    0.08
     subscribe
    0.08
    unsubscribe
    0.08
    blas
    0.08
     subscribing
    0.08
    átek
    0.08
    Subscribe
    0.07
    .gdx
    0.07
    aginator
    0.07
    Activations Density 0.015%

    No Known Activations